ydabke's picture
First Push
e559d5e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.862381637096405,
"min": 0.8137264847755432,
"max": 2.8540990352630615,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8196.0751953125,
"min": 7805.2646484375,
"max": 29134.642578125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.044581413269043,
"min": 0.3387218713760376,
"max": 13.055965423583984,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.693359375,
"min": 65.71204376220703,
"max": 2670.221435546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06754262566349045,
"min": 0.06235437081201121,
"max": 0.07732099537636661,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2701705026539618,
"min": 0.25226799421487195,
"max": 0.37251804858861565,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19701581755105185,
"min": 0.11408315048845229,
"max": 0.29254157104912926,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7880632702042074,
"min": 0.45633260195380915,
"max": 1.4627078552456463,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.636363636363637,
"min": 3.1136363636363638,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 137.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.1136363636363638,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 137.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1765596680",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765597122"
},
"total": 442.5386485309999,
"count": 1,
"self": 0.43190271099979327,
"children": {
"run_training.setup": {
"total": 0.02664396900001975,
"count": 1,
"self": 0.02664396900001975
},
"TrainerController.start_learning": {
"total": 442.0801018510001,
"count": 1,
"self": 0.367131559992913,
"children": {
"TrainerController._reset_env": {
"total": 3.37301025499994,
"count": 1,
"self": 3.37301025499994
},
"TrainerController.advance": {
"total": 438.26335806200734,
"count": 18192,
"self": 0.38037230798613564,
"children": {
"env_step": {
"total": 319.08165941401955,
"count": 18192,
"self": 250.46327713000846,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.40137414000378,
"count": 18192,
"self": 1.287372039025854,
"children": {
"TorchPolicy.evaluate": {
"total": 67.11400210097793,
"count": 18192,
"self": 67.11400210097793
}
}
},
"workers": {
"total": 0.21700814400730906,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.4496590500029,
"count": 18192,
"is_parallel": true,
"self": 220.48415711400605,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029147269999612035,
"count": 1,
"is_parallel": true,
"self": 0.0015168979997497445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001397829000211459,
"count": 10,
"is_parallel": true,
"self": 0.001397829000211459
}
}
},
"UnityEnvironment.step": {
"total": 0.03797151200001281,
"count": 1,
"is_parallel": true,
"self": 0.0008414720001610476,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003986909999866839,
"count": 1,
"is_parallel": true,
"self": 0.0003986909999866839
},
"communicator.exchange": {
"total": 0.034690561999923375,
"count": 1,
"is_parallel": true,
"self": 0.034690561999923375
},
"steps_from_proto": {
"total": 0.0020407869999417017,
"count": 1,
"is_parallel": true,
"self": 0.0003879629997527445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016528240001889571,
"count": 10,
"is_parallel": true,
"self": 0.0016528240001889571
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.96550193599683,
"count": 18191,
"is_parallel": true,
"self": 10.41468327898167,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.683180562006555,
"count": 18191,
"is_parallel": true,
"self": 5.683180562006555
},
"communicator.exchange": {
"total": 167.38735474800706,
"count": 18191,
"is_parallel": true,
"self": 167.38735474800706
},
"steps_from_proto": {
"total": 36.480283347001546,
"count": 18191,
"is_parallel": true,
"self": 6.602916233994961,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.877367113006585,
"count": 181910,
"is_parallel": true,
"self": 29.877367113006585
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.80132634000165,
"count": 18192,
"self": 0.4594071530146948,
"children": {
"process_trajectory": {
"total": 26.237937183987697,
"count": 18192,
"self": 25.71182364798767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5261135360000253,
"count": 4,
"self": 0.5261135360000253
}
}
},
"_update_policy": {
"total": 92.10398200299926,
"count": 90,
"self": 38.16283905199896,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.9411429510003,
"count": 4587,
"self": 53.9411429510003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.160000010713702e-06,
"count": 1,
"self": 1.160000010713702e-06
},
"TrainerController._save_models": {
"total": 0.07660081399990304,
"count": 1,
"self": 0.0007509699998990982,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07584984400000394,
"count": 1,
"self": 0.07584984400000394
}
}
}
}
}
}
}